© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89712
    Prev
    Next
    INDEX
    Explanations

    programming and software development concepts, particularly related to functions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isman
    -0.06
     åŃ
    -0.06
     Wizard
    -0.06
     Hier
    -0.06
     Spir
    -0.06
     dap
    -0.06
    imens
    -0.06
     Mang
    -0.06
     Jog
    -0.06
     Rav
    -0.05
    POSITIVE LOGITS
    fcc
    0.07
     altogether
    0.07
     sondern
    0.07
    ãĥ¼ãĥ³
    0.07
    çĶļ
    0.07
    оло
    0.06
    opt
    0.06
    tones
    0.06
     perse
    0.06
    inkel
    0.06
    Activations Density 0.013%

    No Known Activations